Human–robot collaboration has gained attention in the field of manufacturing and assembly tasks, necessitating the development of adaptable and user-friendly forms of interaction. To address this demand, collaborative robots (cobots) have emerged as a viable solution. Deep Learning has played a pivotal role in enhancing robot capabilities and facilitating their perception and understanding of the environment. This study proposes the integration of cobots and Deep Learning to assist users in assembly tasks such as part handover and storage. The proposed system includes an object classification system to categorize and store assembly elements, a voice recognition system to classify user commands, and a hand-tracking system for close interaction. Tests were conducted for each isolated system and for the complete application as used by different individuals, yielding an average accuracy of 91.25%. The integration of Deep Learning into cobot applications has significant potential for transforming industries, including manufacturing, healthcare, and assistive technologies. This work serves as a proof of concept for the use of several neural networks and a cobot in a collaborative task, demonstrating communication between the systems and proposing an evaluation approach for individual and integrated systems.

Additive manufacturing is widely used to fabricate metamaterials. The mechanical properties of these are tailored by modifying topological parameters to meet desired performance. Here, an auxetic metamaterial composed of arc-shape elements is presented. The directional dependency of the apparent stiffness was characterized through finite element analysis and tensile and compressive tests on additively manufactured samples with fused filament fabrication in thermoplastic polyurethane. Poisson’s ratio was measured with computational vision. The effective Young’s modulus resulted with a nonlinear relation to the wall thickness. The orientation sensibility exposed the relevance of rotational symmetry in a lattice architected metamaterial.

Functionally graded metamaterials represent a cutting-edge approach to designing structures with cellular materials. By manipulating parameters in specific regions, a customized mechanical response is achieved, optimizing material utilization. Despite various proposed methods to generate functionally graded structures, the challenge of high computational costs persists. This study introduces a novel and computationally efficient inverse design method for beams featuring segment-wise graded metamaterials. Using a semi-analytical approach based on Castigliano’s second theorem, this method significantly reduces computational demands. The approach leverages prior experimental and computational characterizations of the transverse deflection in rectangular, reentrant, and hexagonal honeycombs. Validation through finite element models and experimental tests on additively manufactured beams confirms the adequate performance of the method. The proposed framework successfully generates beams with targeted deflections, demonstrating the method’s capability for inverse design under specific loading and boundary conditions. This approach not only optimizes material utilization but also broadens the application scope of functionally graded metamaterials in structural design.

Fruit detection and counting is a key component of data-driven resource management and yield estimation in greenhouses. This work presents a novel infrared-based approach to capsicum counting in greenhouses that takes advantage of the light penetration of infrared (IR) imaging to enhance detection under challenging lighting conditions. The proposed capsicum counting pipeline integrates the YOLO11 detection model for capsicum identification and the BoT-SORT multi-object tracker to track detections across a video stream, enabling accurate fruit counting. The detector model is trained on a dataset of 1000 images, with 11,916 labeled capsicums, captured with an OAK-D pro camera mounted on a mobile robot inside a capsicum greenhouse. On the IR test set, the YOLO11m model achieved an F1-score of 0.82, while the tracker obtained a multiple object tracking accuracy (MOTA) of 0.85, correctly counting 67 of 70 capsicums in a representative greenhouse row. The results demonstrate the effectiveness of this IR-based approach in automating fruit counting in greenhouse environments, offering potential applications in yield estimation.

The rising demand for adaptable and user-friendly forms of interaction in the field of manufacturing and assembly tasks has led to increased attention on human-robot collaboration. Collaborative robots (cobots) have emerged as a promising solution to address this demand. In this study, we propose the integration and application of cobots along with a pre-trained deep learning model to assist users in assembly activities, specifically part handover and storage. The human-robot interaction is facilitated through a hand tracking system that enables a close approach to the user's hand. Testing on the system yielded 99% accuracy. The incorporation of deep learning models in cobot applications holds substantial potential for industry transformation, with implications spanning manufacturing, healthcare, and assistive technologies. This research serves as a compelling proof of concept, showcasing the effective implementation of deep learning models to facilitate close human-robot interactions.